Hyperspectral image spectral-spatial classification via weighted Laplacian smoothing constraint-based sparse representation.

As a powerful tool in hyperspectral image (HSI) classification, sparse representation has gained much attention in recent years owing to its detailed representation of features. In particular, the results of the joint use of spatial and spectral information has been widely applied to HSI classificat...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Eryang Chen, Ruichun Chang, Ke Guo, Fang Miao, Kaibo Shi, Ansheng Ye, Jianghong Yuan
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/93fc8546a12e4543b71ab8e3d8001103
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:93fc8546a12e4543b71ab8e3d8001103
record_format	dspace
spelling	oai:doaj.org-article:93fc8546a12e4543b71ab8e3d80011032021-12-02T20:15:24ZHyperspectral image spectral-spatial classification via weighted Laplacian smoothing constraint-based sparse representation.1932-620310.1371/journal.pone.0254362https://doaj.org/article/93fc8546a12e4543b71ab8e3d80011032021-01-01T00:00:00Zhttps://doi.org/10.1371/journal.pone.0254362https://doaj.org/toc/1932-6203As a powerful tool in hyperspectral image (HSI) classification, sparse representation has gained much attention in recent years owing to its detailed representation of features. In particular, the results of the joint use of spatial and spectral information has been widely applied to HSI classification. However, dealing with the spatial relationship between pixels is a nontrivial task. This paper proposes a new spatial-spectral combined classification method that considers the boundaries of adjacent features in the HSI. Based on the proposed method, a smoothing-constraint Laplacian vector is constructed, which consists of the interest pixel and its four nearest neighbors through their weighting factor. Then, a novel large-block sparse dictionary is developed for simultaneous orthogonal matching pursuit. Our proposed method can obtain a better accuracy of HSI classification on three real HSI datasets than the existing spectral-spatial HSI classifiers. Finally, the experimental results are presented to verify the effectiveness and superiority of the proposed method.Eryang ChenRuichun ChangKe GuoFang MiaoKaibo ShiAnsheng YeJianghong YuanPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 16, Iss 7, p e0254362 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Eryang Chen Ruichun Chang Ke Guo Fang Miao Kaibo Shi Ansheng Ye Jianghong Yuan Hyperspectral image spectral-spatial classification via weighted Laplacian smoothing constraint-based sparse representation.
description	As a powerful tool in hyperspectral image (HSI) classification, sparse representation has gained much attention in recent years owing to its detailed representation of features. In particular, the results of the joint use of spatial and spectral information has been widely applied to HSI classification. However, dealing with the spatial relationship between pixels is a nontrivial task. This paper proposes a new spatial-spectral combined classification method that considers the boundaries of adjacent features in the HSI. Based on the proposed method, a smoothing-constraint Laplacian vector is constructed, which consists of the interest pixel and its four nearest neighbors through their weighting factor. Then, a novel large-block sparse dictionary is developed for simultaneous orthogonal matching pursuit. Our proposed method can obtain a better accuracy of HSI classification on three real HSI datasets than the existing spectral-spatial HSI classifiers. Finally, the experimental results are presented to verify the effectiveness and superiority of the proposed method.
format	article
author	Eryang Chen Ruichun Chang Ke Guo Fang Miao Kaibo Shi Ansheng Ye Jianghong Yuan
author_facet	Eryang Chen Ruichun Chang Ke Guo Fang Miao Kaibo Shi Ansheng Ye Jianghong Yuan
author_sort	Eryang Chen
title	Hyperspectral image spectral-spatial classification via weighted Laplacian smoothing constraint-based sparse representation.
title_short	Hyperspectral image spectral-spatial classification via weighted Laplacian smoothing constraint-based sparse representation.
title_full	Hyperspectral image spectral-spatial classification via weighted Laplacian smoothing constraint-based sparse representation.
title_fullStr	Hyperspectral image spectral-spatial classification via weighted Laplacian smoothing constraint-based sparse representation.
title_full_unstemmed	Hyperspectral image spectral-spatial classification via weighted Laplacian smoothing constraint-based sparse representation.
title_sort	hyperspectral image spectral-spatial classification via weighted laplacian smoothing constraint-based sparse representation.
publisher	Public Library of Science (PLoS)
publishDate	2021
url	https://doaj.org/article/93fc8546a12e4543b71ab8e3d8001103
work_keys_str_mv	AT eryangchen hyperspectralimagespectralspatialclassificationviaweightedlaplaciansmoothingconstraintbasedsparserepresentation AT ruichunchang hyperspectralimagespectralspatialclassificationviaweightedlaplaciansmoothingconstraintbasedsparserepresentation AT keguo hyperspectralimagespectralspatialclassificationviaweightedlaplaciansmoothingconstraintbasedsparserepresentation AT fangmiao hyperspectralimagespectralspatialclassificationviaweightedlaplaciansmoothingconstraintbasedsparserepresentation AT kaiboshi hyperspectralimagespectralspatialclassificationviaweightedlaplaciansmoothingconstraintbasedsparserepresentation AT anshengye hyperspectralimagespectralspatialclassificationviaweightedlaplaciansmoothingconstraintbasedsparserepresentation AT jianghongyuan hyperspectralimagespectralspatialclassificationviaweightedlaplaciansmoothingconstraintbasedsparserepresentation
_version_	1718374595841490944

Hyperspectral image spectral-spatial classification via weighted Laplacian smoothing constraint-based sparse representation.

Ejemplares similares